Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5772 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8452. Min Range: -4.8452

Max Act: 4.8452. Min Act: -0.0000

Data Index: 1631290 (Python Code)

Max Activating Token Index: 760

Text #1

Max Range: 4.8452. Min Range: -4.8452

Max Act: 4.1942. Min Act: -0.0000

Data Index: 1563221 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.9963. Min Act: -0.0000

Data Index: 1616785 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.6804. Min Act: -0.0000

Data Index: 1486442 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.6641. Min Act: -0.0000

Data Index: 1366029 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.9381. Min Act: -0.0000

Data Index: 1616383 (Python Code)

Max Activating Token Index: 670

Text #6

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.9500. Min Act: -0.0000

Data Index: 1551274 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 4.8452. Min Range: -4.8452

Max Act: 4.0994. Min Act: -0.0000

Data Index: 1583423 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.8480. Min Act: -0.0000

Data Index: 1621573 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 4.8452. Min Range: -4.8452

Max Act: 4.0055. Min Act: -0.0000

Data Index: 1449875 (Python Code)

Max Activating Token Index: 719

Text #10

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.7882. Min Act: -0.0000

Data Index: 1435695 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.7697. Min Act: -0.0000

Data Index: 1648893 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.7422. Min Act: -0.0000

Data Index: 1443386 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.4176. Min Act: -0.0000

Data Index: 1390696 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.5954. Min Act: -0.0000

Data Index: 841157 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.5328. Min Act: -0.0000

Data Index: 1391798 (Python Code)

Max Activating Token Index: 124

Text #16

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.6750. Min Act: -0.0000

Data Index: 1566270 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.3415. Min Act: -0.0000

Data Index: 1471396 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.4885. Min Act: -0.0000

Data Index: 1364313 (Python Code)

Max Activating Token Index: 485

Text #19

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.3331. Min Act: -0.0000

Data Index: 1646894 (Python Code)

Max Activating Token Index: 613